© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 546
    Prev
    Next
    INDEX
    Explanations

    iostream, stdlib, path, string

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spotlights press‐release metadata headers (e.g. “MARKETWIRED,” “GLOBE NEWSWIRE,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     достиг
    0.32
    ...).
    0.30
    /=
    0.29
     nearing
    0.28
     dezelfde
    0.27
    된
    0.27
    되지
    0.26
    不超过
    0.26
     brisk
    0.26
     diterapkan
    0.26
    POSITIVE LOGITS
     және
    0.32
     ਅਤੇ
    0.31
     Fernando
    0.28
    enzie
    0.27
     ಮತ್ತು
    0.27
     ،
    0.26
    ;
    0.26
    ur
    0.25
     һәм
    0.25
     एवं
    0.25
    Activations Density 0.001%

    No Known Activations